© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78725
    Prev
    Next
    INDEX
    Explanations

    by followed by names or dates

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron chiefly activates on numeric tokens (e.g. years, measurements, and other numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bereits
    -0.93
     вже
    -0.85
    hão
    -0.85
     changes
    -0.83
     cedera
    -0.80
    jema
    -0.79
     strives
    -0.79
     greatly
    -0.79
    SOLD
    -0.77
    “
    -0.75
    POSITIVE LOGITS
    atories
    1.02
     découvrir
    0.91
    good
    0.89
     MPC
    0.87
     discovery
    0.85
     discover
    0.83
     découvre
    0.82
    give
    0.82
     descobri
    0.82
     Robotic
    0.82
    Activations Density 0.003%

    No Known Activations